我正在尝试从mongodb进行简单的检索（工作正常），以便将其用作Spark的RDD。问题是，当我使用Hadoop API保存时，它会抛出驱动程序堆栈跟踪。有趣的是，它确实打开了与我本地mongodb实例的连接，因为我可以在mongodb的连接打开/结束日志中看到。下面是代码片段，pom.xml和它抛出的异常。另外，我使用以下Mongodb连接器用于Hadoop： https://github.com/mongodb/mongo-hadoop
SparkConf sc = new SparkConf()
.setMaster("local[3]")
.setAppName("Spark-Mongo demo");
JavaSparkContext jsc = new JavaSparkContext(sc);
mgconfig.set("mongo.job.input.format",
"com.mongodb.hadoop.MongoInputFormat");
mgconfig.set("mongo.input.uri",
"mongodb://localhost:27017/test.apSlime");
JavaPairRDD<Object, BSONObject> documents = jsc.newAPIHadoopRDD(
mgconfig, // Configuration
MongoInputFormat.class, // InputFormat: read from a live cluster.
Object.class, // Key class
BSONObject.class // Value class
);
Configuration outputConfig = new Configuration();
outputConfig.set("mongo.job.output.format",
"com.mongodb.hadoop.MongoOutputFormat");
outputConfig.set("mongo.output.uri",
"mongodb://localhost:27017/test.spark");
documents.saveAsNewAPIHadoopFile(
"file:///this-is-completely-unused",
Object.class,
BSONObject.class,
MongoOutputFormat.class,
outputConfig
);
例外：
16:12:57.055 ERROR org.apache.spark.scheduler.TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.NullPointerException
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1012)
at org.apache.hadoop.util.Shell.runCommand(Shell.java:483)
at org.apache.hadoop.util.Shell.run(Shell.java:456)
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:722)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:815)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:798)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:731)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:225)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:209)
at org.apache.hadoop.fs.RawLocalFileSystem.createOutputStreamWithMode(RawLocalFileSystem.java:305)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:294)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:326)
at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSOutputSummer.<init>(ChecksumFileSystem.java:393)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:456)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:435)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:909)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:890)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:787)
at com.mongodb.hadoop.output.MongoRecordWriter.<init>(MongoRecordWriter.java:75)
at com.mongodb.hadoop.MongoOutputFormat.getRecordWriter(MongoOutputFormat.java:46)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1107)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1091)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1922)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1146)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1074)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1074)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopDataset(PairRDDFunctions.scala:1074)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply$mcV$sp(PairRDDFunctions.scala:994)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply(PairRDDFunctions.scala:985)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply(PairRDDFunctions.scala:985)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopFile(PairRDDFunctions.scala:985)
at org.apache.spark.api.java.JavaPairRDD.saveAsNewAPIHadoopFile(JavaPairRDD.scala:800)
at javademo.SparkMongoDemo.main(SparkMongoDemo.java:57)
Caused by: java.lang.NullPointerException
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1012)
at org.apache.hadoop.util.Shell.runCommand(Shell.java:483)
at org.apache.hadoop.util.Shell.run(Shell.java:456)
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:722)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:815)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:798)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:731)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:225)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:209)
at org.apache.hadoop.fs.RawLocalFileSystem.createOutputStreamWithMode(RawLocalFileSystem.java:305)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:294)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:326)
at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSOutputSummer.<init>(ChecksumFileSystem.java:393)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:456)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:435)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:909)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:890)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:787)
at com.mongodb.hadoop.output.MongoRecordWriter.<init>(MongoRecordWriter.java:75)
at com.mongodb.hadoop.MongoOutputFormat.getRecordWriter(MongoOutputFormat.java:46)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1107)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1091)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
的pom.xml：
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>Jas.demo</groupId>
<artifactId>spark</artifactId>
<version>1.0-SNAPSHOT</version>
<!-- <parent>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-parent</artifactId>
<version>1.3.5.RELEASE</version>
</parent>-->
<properties>
<java.version>1.8</java.version>
</properties>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
<configuration>
<source>${java.version}</source>
<target>${java.version}</target>
</configuration>
</plugin>
</plugins>
</build>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-yarn-api</artifactId>
<version>2.6.0</version>
</dependency>
<dependency>
<groupId>org.mongodb</groupId>
<artifactId>mongo-java-driver</artifactId>
<version>3.2.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>1.6.1</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_2.11</artifactId>
<version>1.6.1</version>
</dependency>
<dependency>
<groupId>org.mongodb.mongo-hadoop</groupId>
<artifactId>mongo-hadoop-core</artifactId>
<version>1.5.1</version>
</dependency>
</dependencies>
</project>